Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcs.LG
MAML with over-parameterized DNNs converges globally at a linear rate.
problem Few-shot learning with limited data.
method Model-agnostic meta-learning (MAML) with over-parameterized deep neural networks (DNNs).
result MAML with over-parameterized DNNs converges globally at a linear rate.